中文
相关论文

相关论文: Expanding before Inferring: Enhancing Factuality i…

200 篇论文

As Large Language Models (LLMs) continue to advance, they are increasingly relied upon as real-time sources of information by non-expert users. To ensure the factuality of the information they provide, much research has focused on…

计算与语言 · 计算机科学 2025-04-07 Yining Wang , Yuquan Wang , Xi Li , Mi Zhang , Geng Hong , Min Yang

Despite the recent progress in news summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation. Unlike previous…

计算与语言 · 计算机科学 2025-02-17 Huawen Feng , Yan Fan , Xiong Liu , Ting-En Lin , Zekun Yao , Yuchuan Wu , Fei Huang , Yongbin Li , Qianli Ma

Large language models (LLMs) are susceptible to generating inaccurate or false information, often referred to as "hallucinations" or "confabulations." While several technical advancements have been made to detect hallucinated content by…

人机交互 · 计算机科学 2025-08-12 Hyo Jin Do , Rachel Ostrand , Werner Geyer , Keerthiram Murugesan , Dennis Wei , Justin Weisz

Hallucination detection has become increasingly important for improving the reliability of large language models (LLMs). Recently, hybrid approaches such as HaMI, which combine semantic consistency with internal model states via Multiple…

计算与语言 · 计算机科学 2026-05-14 Shota Fujikawa , Issei Sato

Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage, but suffer from hallucinations where they choose incorrect tools, provide malformed parameters and exhibit 'tool bypass' behavior by performing…

人工智能 · 计算机科学 2026-01-09 Kait Healy , Bharathi Srinivasan , Visakh Madathil , Jing Wu

Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time methods steer LLM representations toward the "truthful…

计算与语言 · 计算机科学 2024-06-10 Farima Fatahi Bayat , Xin Liu , H. V. Jagadish , Lu Wang

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

计算与语言 · 计算机科学 2024-04-12 Linyi Yang , Shuibai Zhang , Zhuohao Yu , Guangsheng Bao , Yidong Wang , Jindong Wang , Ruochen Xu , Wei Ye , Xing Xie , Weizhu Chen , Yue Zhang

The detection of sophisticated hallucinations in Large Language Models (LLMs) is hampered by a ``Detection Dilemma'': methods probing internal states (Internal State Probing) excel at identifying factual inconsistencies but fail on logical…

计算与语言 · 计算机科学 2026-01-09 Yusheng Song , Lirong Qiu , Xi Zhang , Zhihao Tang

Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health…

计算与语言 · 计算机科学 2024-09-20 Sumera Anjum , Hanzhi Zhang , Wenjun Zhou , Eun Jin Paek , Xiaopeng Zhao , Yunhe Feng

Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite advances in alignment and instruction tuning, LLMs can still…

计算与语言 · 计算机科学 2025-05-02 Makoto Sato

When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating…

计算与语言 · 计算机科学 2024-10-02 Zorik Gekhman , Gal Yona , Roee Aharoni , Matan Eyal , Amir Feder , Roi Reichart , Jonathan Herzig

Hallucinations in Large Language Models (LLMs) are widely regarded as errors - outputs that deviate from factual accuracy. However, in creative or exploratory contexts, these "mistakes" may represent unexpected avenues for innovation. We…

人工智能 · 计算机科学 2025-04-17 Kris Pilcher , Esen K. Tütüncü

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

机器学习 · 计算机科学 2024-07-02 Xiaoling Zhou , Wei Ye , Yidong Wang , Chaoya Jiang , Zhemg Lee , Rui Xie , Shikun Zhang

Large Language Models (LLMs) have significantly advanced communications fields, such as Telecom Q\&A, mathematical modeling, and coding. However, LLMs encounter an inherent issue known as hallucination, i.e., generating fact-conflicting or…

网络与互联网体系结构 · 计算机科学 2024-12-10 Yinqiu Liu , Guangyuan Liu , Ruichen Zhang , Dusit Niyato , Zehui Xiong , Dong In Kim , Kaibin Huang , Hongyang Du

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but…

计算与语言 · 计算机科学 2026-05-25 Paul Landes , Pranav Herur , Adam Cross , Jimeng Sun

Generating semantically coherent text requires a robust internal representation of linguistic structures, which traditional embedding techniques often fail to capture adequately. A novel approach, Latent Lexical Projection (LLP), is…

计算与语言 · 计算机科学 2025-03-26 Ziad Shaker , Brendan Ashdown , Hugo Fitzalan , Alistair Heathcote , Jocasta Huntington

Large language models (LLMs) demonstrate strong capabilities in natural language processing but remain prone to hallucinations, generating factually incorrect or fabricated content. This issue undermines their reliability, particularly in…

计算与语言 · 计算机科学 2025-02-19 Cheng Peng Huang , Hao-Yuan Chen

Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solely of true statements, language models still generate…

计算与语言 · 计算机科学 2024-07-12 Yuji Zhang , Sha Li , Jiateng Liu , Pengfei Yu , Yi R. Fung , Jing Li , Manling Li , Heng Ji

The remarkable capabilities of large language models have been accompanied by a persistent drawback: the generation of false and unsubstantiated claims commonly known as "hallucinations". To combat this issue, recent research has introduced…

计算与语言 · 计算机科学 2023-05-25 Anthony Chen , Panupong Pasupat , Sameer Singh , Hongrae Lee , Kelvin Guu

Despite their impressive capacities, Large language models (LLMs) often struggle with the hallucination issue of generating inaccurate or fabricated content even when they possess correct knowledge. In this paper, we extend the exploration…

计算与语言 · 计算机科学 2025-02-06 Jialiang Wu , Yi Shen , Sijia Liu , Yi Tang , Sen Song , Xiaoyi Wang , Longjun Cai